© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31740
    Prev
    Next
    INDEX
    Explanations

    grab data or files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    举æŃ¢
    -0.10
    æİ¥åıĹ
    -0.10
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.10
    ä¼Ļä¼´åħ³ç³»
    -0.09
    æī¿åıĹ
    -0.09
    ä»ĺåĩº
    -0.09
    æĪ¿éĹ´éĩĮ
    -0.09
    .rev
    -0.09
    æ®·
    -0.09
    ctp
    -0.09
    POSITIVE LOGITS
    ä¸ĢæĬĬ
    0.15
    åıijå±ķæľºéģĩ
    0.10
    æľºéģĩ
    0.10
    çģµæĦŁ
    0.09
    ä¸Ģçľĭ
    0.09
    cue
    0.09
    å§Ķ书记
    0.08
    常说
    0.08
    è¯Ŀè¯ŃæĿĥ
    0.08
    æĬĵ
    0.08
    Activations Density 0.025%

    No Known Activations